Hello Dhananjay,
On 6/24/2024 11:28 AM, Dhananjay Ugwekar wrote:
Currently the energy-cores event in the power PMU aggregates energy
consumption data at a package level. On the other hand the core energy
RAPL counter in AMD CPUs has a core scope (which means the energy
consumption is recorded se
Add a new "power_per_core" PMU and "energy-per-core" event for
monitoring energy consumption by each core. The existing energy-cores
event aggregates the energy consumption at the package level.
This new event aligns with the AMD's per_core energy counters.
Tested the package level and core level
After making the rapl_model struct global, the rapl_msrs global
variable isn't needed, so remove it.
Also it will be cleaner when new per-core scope PMU is added. As we will
need to maintain two rapl_msrs array(one for per-core scope and one for
package scope PMU), inside the rapl_model struct.
S
Prep for addition of power_per_core PMU to handle core scope energy
consumption for AMD CPUs.
Replace the generic names with *_pkg*, to differentiate between the
scopes of the two different PMUs and their variables.
No functional change.
Signed-off-by: Dhananjay Ugwekar
---
arch/x86/events/rap
Prep for per-core RAPL PMU addition.
No functional change.
Signed-off-by: Dhananjay Ugwekar
---
arch/x86/events/rapl.c | 15 ++-
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 70c7b35fb4d2..f815c60ec551 100644
---
This is in preparation for the addition of per-core RAPL counter support
for AMD CPUs.
The CPU online and offline functions will need to handle the setting up and
migration of the new per-core PMU as well. The wrapper functions added
below will make it easier to pass the corresponding args for bot
This patch is in preparation for addition of per-core energy counter
support for AMD CPUs.
Per-core energy counter PMU will need a separate cpumask. It seems like
a better approach to add the cpumask inside the rapl_pmus struct, instead
of creating another global cpumask variable for per-core PMU.
To support AMD's per_core RAPL counter, we will need to check
per_core capability of the current rapl_model multiple times in
rapl_cpu_online/offline, init_rapl_pmus functions, so cache the
matched rapl model in a global variable, to avoid calling
x86_match_cpu() multiple times.
No functional chan
Rename struct rapl_pmu variables from "pmu" to "rapl_pmu", to
avoid any confusion between the variables of two different
structs pmu and rapl_pmu. As rapl_pmu also contains a pointer to
struct pmu, which leads to situations in code like pmu->pmu,
which is needlessly confusing. Above scenario is rep
After commit ("x86/cpu/topology: Add support for the AMD 0x8026 leaf"),
on AMD processors that support extended CPUID leaf 0x8026, the
topology_die_cpumask() and topology_logical_die_id() macros, no longer
return the package cpumask and package id, instead they return the CCD
(Core Complex
From: K Prateek Nayak
On x86, topology_core_id() returns a unique core ID within the PKG
domain. Looking at match_smt() suggests that a core ID just needs to be
unique within a LLC domain. For use cases such as the per-core RAPL PMU,
there exists a need for a unique core ID across the entire syst
Currently the energy-cores event in the power PMU aggregates energy
consumption data at a package level. On the other hand the core energy
RAPL counter in AMD CPUs has a core scope (which means the energy
consumption is recorded separately for each core). Earlier efforts to add
the core event in t
12 matches
Mail list logo
